diff --git a/roberta.py b/roberta.py
index f4d7765..ad0f479 100644
--- a/roberta.py
+++ b/roberta.py
@@ -22,7 +22,6 @@ class RobertaLeakyHead(nn.Module):
         classifier_dropout = (
             config.classifier_dropout if config.classifier_dropout is not None else config.hidden_dropout_prob
         )
-        self.leaky_relu = nn.LeakyReLU()
         self.dropout = nn.Dropout(classifier_dropout)
         self.out_proj = nn.Linear(hidden_size, config.num_labels)
 
@@ -78,17 +77,17 @@ class RobertaLeaky(RobertaForSequenceClassification):
         self.post_init()
 
     def forward(
-        self,
-        input_ids: Optional[torch.LongTensor] = None,
-        attention_mask: Optional[torch.FloatTensor] = None,
-        token_type_ids: Optional[torch.LongTensor] = None,
-        position_ids: Optional[torch.LongTensor] = None,
-        head_mask: Optional[torch.FloatTensor] = None,
-        inputs_embeds: Optional[torch.FloatTensor] = None,
-        labels: Optional[torch.LongTensor] = None,
-        output_attentions: Optional[bool] = None,
-        output_hidden_states: Optional[bool] = None,
-        return_dict: Optional[bool] = None,
+            self,
+            input_ids: Optional[torch.LongTensor] = None,
+            attention_mask: Optional[torch.FloatTensor] = None,
+            token_type_ids: Optional[torch.LongTensor] = None,
+            position_ids: Optional[torch.LongTensor] = None,
+            head_mask: Optional[torch.FloatTensor] = None,
+            inputs_embeds: Optional[torch.FloatTensor] = None,
+            labels: Optional[torch.LongTensor] = None,
+            output_attentions: Optional[bool] = None,
+            output_hidden_states: Optional[bool] = None,
+            return_dict: Optional[bool] = None,
     ) -> Union[Tuple[torch.Tensor], SequenceClassifierOutput]:
         r"""
         labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):